* [RuFlo v3.56.0](https://github.com/ruvnet/ruflo) – Enterprise-grade multi-agent orchestration platform for deploying, coordinating, and optimizing specialized AI agents.

* [PentAGI v2.2.0](https://github.com/vxcontrol/pentagi) – Autonomous AI-driven penetration testing platform that runs sandboxed attacks, orchestrates specialized agents, and produces detailed vulnerability reports.

* [Neo.mjs 13.2.0](https://github.com/neomjs/neo) – Modern JavaScript framework for building feature-rich web applications with multi-threading support.

* [Hive v5.162.0](https://github.com/hivecommons/hive) – Hive orchestrates AI agents for issue and pull request workflows in Go, using deterministic shell pipelines for governance before LLM-driven judgment and PR creation.

* [Strands Agents python/v1.60.0](https://github.com/strands-agents/harness-sdk) – Model-driven SDK for building and running AI agents, with customizable agent loops, multi-agent workflows, and model-agnostic providers.

* [AI Maestro v0.62.0](https://github.com/23blocks-OS/ai-maestro) – Agent orchestrator providing persistent memory, agent-to-agent messaging, and a dashboard to manage agents across multiple machines.

* [ReevesAgents v1.8.0](https://github.com/mertkayacs/reevesagents) – Local tmux-first workspace that lets one AI coding agent spawn, steer, and supervise other agent CLIs via MCP with shared TUI, Web UI, and CLI control.

* [REDCELL v0.12.0](https://github.com/martian56/redcell) – REDCELL orchestrates LLM agents to execute real penetration testing in a Kali container and generate structured reports with live operator control.

* [TaskTrooper v0.3.0](https://github.com/makifbaysal/tasktrooper) – Local-first agent platform that runs task-based role agents to plan, implement, test, and open pull requests locally on your machine.

* [Antares v0.6.0](https://github.com/enowdev/antares) – Self-hosted AI pentest agent and assistant providing an authorized security testing workspace with files, shell, real browser control, memory, and retrieval-augmented reports.

* [OpenSwarm v0.24.4](https://github.com/Intrect-io/OpenSwarm) – Orchestrates multiple Claude Code agents to convert Linear issues into code via Worker/Reviewer pipelines, with Discord reporting and LanceDB-backed memory.

* [MetaHarness v0.4.17](https://github.com/ruvnet/metaharness) – A meta agent-harness factory that generates repo-scoped MCP servers, memory, skills, and witness-signed release provenance from a GitHub URL or blank slate.

* [Warren v0.19.2](https://github.com/jayminwest/warren) – Self-hostable control plane that spawns ephemeral, sandboxed coding agents on GitHub repos, streams events, and returns a branch for PRs.

* [useAgent native-runtime-3ab52...](https://github.com/useagenthq/useagent) – Provider-neutral AI coworker that runs durable, event-sourced agent sessions with isolated Linux sandboxes and team context to produce complete artifacts and PRs.

* [trackinizer v0.1.6](https://github.com/rekursiv-ai/trackinizer) – Centralized database for managing agent and human inquiries, knowledge, and work with a FastAPI backend over Postgres.

* [Festival v0.3.19](https://github.com/Obedience-Corp/festival) – Standardized workspace and workflow for AI agents, combining version-controlled context with structured methodology plans for long-running, verifiable work.

* [Errand v0.2.6](https://github.com/runta-dev/errand) – Desktop app for running persistent AI agents on cloud computers, with per-agent conversations, live work viewing, and saved workspace continuity.

* [LobsterAI 2026.9.23](https://github.com/netease-youdao/LobsterAI) – 24/7 personal assistant agent that executes tasks, automates workflows, runs code locally or in a sandbox, and supports IM control.